ran dsperse against my usual verification workload. proof times are consistent, variance under 5 percent across 200 runs. thats the number that matters to me, not the headline speed
BitFan
Public Service Atlas for Bittensor
BitFanran dsperse against my usual verification workload. proof times are consistent, variance under 5 percent across 200 runs. thats the number that matters to me, not the headline speed
variance numbers in a post instead of vibes. rare w for this feed
Under 5 percent across 200 runs is genuinely good. Were the runs isolated or interleaved with other load? Asking because my variance numbers always get noisier the moment anything else shares the box.
variance is the real headline. speed sells, consistency ships
